Latent Factor Modeling with Expert Network for Multi-Behavior Recommendation

2026-03-19

AI Summary

This work addresses the limitations of existing recommendation approaches, which either model only a single user behavior—suffering from data sparsity—or conflate multiple behavioral signals, thereby obscuring distinct user intents. To overcome these issues, the authors propose a Gated Mixture-of-Experts architecture that decouples latent factors to enable fine-grained modeling of multi-behavioral interactions. Specifically, a gating mechanism dynamically aggregates expert representations to accurately capture user preferences, while self-supervised learning is incorporated to enhance both expert independence and factor consistency. Extensive experiments on three real-world datasets demonstrate that the proposed method significantly outperforms state-of-the-art baselines, achieving notable improvements in both performance and robustness for multi-behavior recommendation tasks.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Data Mining & Knowledge Management: Recommender Systems
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Traditional recommendation methods, which typically focus on modeling a single user behavior (e.g., purchase), often face severe data sparsity issues. Multi-behavior recommendation methods offer a promising solution by leveraging user data from diverse behaviors. However, most existing approaches entangle multiple behavioral factors, learning holistic but imprecise representations that fail to capture specific user intents. To address this issue, we propose a multi-behavior method by modeling latent factors with an expert network (MBLFE). In our approach, we design a gating expert network, where the expert network models all latent factors within the entire recommendation scenario, with each expert specializing in a specific latent factor. The gating network dynamically selects the optimal combination of experts for each user, enabling a more accurate representation of user preferences. To ensure independence among experts and factor consistency of a particular expert, we incorporate self-supervised learning during the training process. Furthermore, we enrich embeddings with multi-behavior data to provide the expert network with more comprehensive collaborative information for factor extraction. Extensive experiments on three real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines, validating its effectiveness.

Problem

• multi-behavior recommendation
• data sparsity
• latent factor modeling
• user intent
• behavioral factors

Innovation

• expert network
• latent factor modeling
• multi-behavior recommendation
• gating mechanism
• self-supervised learning